© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97076
    Prev
    Next
    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    缴æİ¥
    -0.30
    åı¯ä»¥çĽ´æİ¥
    -0.28
    缴è§Ĥ
    -0.28
    .Dto
    -0.28
    refix
    -0.26
     Sr
    -0.26
     directly
    -0.25
    èĩªçĦ¶æĺ¯
    -0.25
     const
    -0.25
    shal
    -0.24
    POSITIVE LOGITS
     appropriate
    0.38
     acceptable
    0.32
    åIJĪéĢĤçļĦ
    0.31
     adequate
    0.31
    åIJĪéĢĤ
    0.30
     compatible
    0.30
    éĢĤå®ľ
    0.30
    è¿ĻäºĽå¹´
    0.29
    appropriate
    0.29
     appropri
    0.29
    Activations Density 0.004%

    No Known Activations